Stable Signature is Unstable: Removing Image Watermark from Diffusion Models
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866929340793487360 |
|---|---|
| author | Hu, Yuepeng Jiang, Zhengyuan Guo, Moyang Gong, Neil |
| author_facet | Hu, Yuepeng Jiang, Zhengyuan Guo, Moyang Gong, Neil |
| contents | Watermark has been widely deployed by industry to detect AI-generated images. A recent watermarking framework called \emph{Stable Signature} (proposed by Meta) roots watermark into the parameters of a diffusion model's decoder such that its generated images are inherently watermarked. Stable Signature makes it possible to watermark images generated by \emph{open-source} diffusion models and was claimed to be robust against removal attacks. In this work, we propose a new attack to remove the watermark from a diffusion model by fine-tuning it. Our results show that our attack can effectively remove the watermark from a diffusion model such that its generated images are non-watermarked, while maintaining the visual quality of the generated images. Our results highlight that Stable Signature is not as stable as previously thought. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_07145 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Stable Signature is Unstable: Removing Image Watermark from Diffusion Models Hu, Yuepeng Jiang, Zhengyuan Guo, Moyang Gong, Neil Cryptography and Security Computer Vision and Pattern Recognition Watermark has been widely deployed by industry to detect AI-generated images. A recent watermarking framework called \emph{Stable Signature} (proposed by Meta) roots watermark into the parameters of a diffusion model's decoder such that its generated images are inherently watermarked. Stable Signature makes it possible to watermark images generated by \emph{open-source} diffusion models and was claimed to be robust against removal attacks. In this work, we propose a new attack to remove the watermark from a diffusion model by fine-tuning it. Our results show that our attack can effectively remove the watermark from a diffusion model such that its generated images are non-watermarked, while maintaining the visual quality of the generated images. Our results highlight that Stable Signature is not as stable as previously thought. |
| title | Stable Signature is Unstable: Removing Image Watermark from Diffusion Models |
| topic | Cryptography and Security Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2405.07145 |